Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Dendrocentric learning for synthetic intelligence


Artificial intelligence now advances by performing twice as many floating-point multiplications every two months, but the semiconductor industry tiles twice as many multipliers on a chip every two years. Moreover, the returns from tiling these multipliers ever more densely now diminish because signals must travel relatively farther and farther. Although travel can be shortened by stacking tiled multipliers in a three-dimensional chip, such a solution acutely reduces the available surface area for dissipating heat. Here I propose to transcend this three-dimensional thermal constraint by moving away from learning with synapses to learning with dendrites. Synaptic inputs are not weighted precisely but rather ordered meticulously along a short stretch of dendrite, termed dendrocentric learning. With the help of a computational model of a dendrite and a conceptual model of a ferroelectric device that emulates it, I illustrate how dendrocentric learning artificial intelligence—or synthetic intelligence for short—could run not with megawatts in the cloud but rather with watts on a smartphone.

This is a preview of subscription content, access via your institution

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Demand of AI for flops is growing unsustainably.
Fig. 2: The energy a synthetic brain consumes could scale with its neurons like a biological brain.
Fig. 3: A short stretch of dendrite could detect a consecutive spike sequence.
Fig. 4: Concept for a dendrite-like nanoscale device and its 3D integration.

Code availability

The Mathematica notebook used to simulate and analyse the dendrite model is available  at


  1. Brown, T. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877–1901 (2020).

    Google Scholar 

  2. GPT-3. A robot wrote this article. Are you scared yet, human? The Guardian (2020);

  3. Mehonic, A. & Kenyon, A. Brain-inspired computing needs a master plan. Nature 604, 255–260 (2022).

    Article  CAS  PubMed  Google Scholar 

  4. Dally, W., Turakhia, Y. & Han, S. Domain-specific hardware accelerators. Commun. ACM 63, 48–57 (2020).

    Article  Google Scholar 

  5. Jouppi, N. et al. A domain-specific supercomputer for training deep neural networks. Commun. ACM 63, 67–78 (2020).

    Article  Google Scholar 

  6. Rosenblatt, F. The perceptron—a probabilistic model for information-storage and organization in the brain. Psychol. Rev. 65, 386–408 (1958). This paper introduced the synaptocentric conception of the learning brain.

    Article  CAS  PubMed  Google Scholar 

  7. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    Article  CAS  PubMed  Google Scholar 

  8. Schmidhuber, J. Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015).

    Article  PubMed  Google Scholar 

  9. Radford, A. et al. Language models are unsupervised multitask learners. OpenAI Blog 1, 9 (2019).

    Google Scholar 

  10. Anthony, L. F. W., Kanding, B. & Selvan, R. Carbontracker: tracking and predicting the carbon footprint of training deep learning models. Preprint at (2020).

  11. Dally, W. J. et al. Hardware-enabled artificial intelligence. In 2018 IEEE Symposium on VLSI Circuits 3–6 (IEEE, 2018).

  12. Goda, A. 3-D NAND technology achievements and future scaling perspectives. IEEE Trans. Electron Devices 67, 1373–1381 (2020).

    Article  CAS  Google Scholar 

  13. Pekny, T. et al. A 1-Tb Density 4b/Cell 3D-NAND Flash on 176-Tier Technology with 4-Independent Planes for Read using CMOS-Under-the-Array. In 2022 IEEE International Solid-State Circuits Conference (ISSCC) 1–3 (IEEE, 2022).

  14. Markram, H. et al. Reconstruction and simulation of neocortical microcircuitry. Cell 163, 456–492 (2015).

    Article  CAS  PubMed  Google Scholar 

  15. Park, Y. et al. 3-D stacked synapse array based on charge-trap flash memory for implementation of deep neural networks. IEEE Trans. Electron Devices 66, 420–427 (2019).

    Article  CAS  Google Scholar 

  16. Bavandpour, M., Sahay, S., Mahmoodi, M. R. & Strukov, D. B. 3D-aCortex: an ultra-compact energy-efficient neurocomputing platform based on commercial 3D-NAND flash memories. Neuromorph. Comput. Eng. 1, 014001 (2021).

    Article  Google Scholar 

  17. Thorpe, S., Delorme, A. & Van Rullen, R. Spike-based strategies for rapid processing. Neural Netw. 14, 715–725 (2001).

    Article  CAS  PubMed  Google Scholar 

  18. Skaggs, W. E. & McNaughton, B. L. Replay of neuronal firing sequences in rat hippocampus during sleep following spatial experience. Science 271, 1870–1873 (1996).

    Article  CAS  PubMed  Google Scholar 

  19. Wehr, M. & Laurent, G. Odour encoding by temporal sequences of firing in oscillating neural assemblies. Nature 384, 162–166 (1996).

    Article  CAS  PubMed  Google Scholar 

  20. Vaz, A. P., Wittig, J. H., Inati, S. K. & Zaghloul, K. A. Replay of cortical spiking sequences during human memory retrieval. Science 367, 1131–1134 (2020). A specific sequence of spikes encodes memory of an episode in humans and recall involves reinstating this temporal order of activity.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  21. Hanin, B. & Rolnick, D. Deep ReLU networks have surprisingly few activation patterns. In 33rd Conference on Neural Information Processing Systems (NeurIPS, 2019)

  22. Cai, X., Huang, J., Bian, Y. & Church, K. Isotropy in the contextual embedding space: Clusters and manifolds. In International Conference on Learning Representations (ICLR, 2021).

  23. Herculano-Houzel, S. Scaling of brain metabolism with a fixed energy budget per neuron: implications for neuronal activity, plasticity and evolution. PLoS ONE 6, e17514 (2011).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Sterling, P. & Laughlin, S. Principles of Neural Design (MIT, 2015).

  25. Hemberger, M., Shein-Idelson, M., Pammer, L. & Laurent, G. Reliable sequential activation of neural assemblies by single pyramidal cells in a three-layered cortex. Neuron 104, 353–369.e5 (2019).

    Article  CAS  PubMed  Google Scholar 

  26. Ishikawa, T. & Ikegaya, Y. Locally sequential synaptic reactivation during hippocampal ripples. Sci. Adv. (2020). Neighbouring spines are activated serially along a dendrite, towards or away from the cell body.

  27. Agmonsnir, H. & Segev, I. Signal delay and input synchronization in passive dendritic structures. J. Neurophysiol. 70, 2066–2085 (1993).

    Article  CAS  PubMed  Google Scholar 

  28. Iacobucci, G. & Popescu, G. NMDA receptors: linking physiological output to biophysical operation. Nat. Rev. Neurosci. 18, 236–249 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. Branco, T., Clark, B. & Hausser, M. Dendritic discrimination of temporal input sequences in cortical neurons. Science 329, 1671–1675 (2010).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Matsuzaki, M. et al. Dendritic spine geometry is critical for AMPA receptor expression in hippocampal CA1 pyramidal neurons. Nat. Neurosci. 4, 1086–1092 (2001).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  31. Kerlin, A. et al. Functional clustering of dendritic activity during decision-making. eLife (2019). Task-associated calcium signals cluster within branches over approximately 10 μm, potentially supporting a large learning capacity in individual neurons.

  32. Shoemaker, P. Neural bistability and amplification mediated by NMDA receptors: analysis of stationary equations. Neurocomputing 74, 3058–3071 (2011).

    Article  Google Scholar 

  33. Major, G., Polsky, A., Denk, W., Schiller, J. & Tank, D. Spatiotemporally graded NMDA spike/plateau potentials in basal dendrites of neocortical pyramidal neurons. J. Neurophysiol. 99, 2584–2601 (2008).

    Article  CAS  PubMed  Google Scholar 

  34. Fino, E. et al. RuBi-glutamate: two-photon and visible-light photoactivation of neurons and dendritic spines. Front. Neural Circuits (2009).

  35. Mahowald, M. & Douglas, R. A silicon neuron. Nature 354, 515–518 (1991).

    Article  CAS  PubMed  Google Scholar 

  36. Benjamin, B. et al. Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc. IEEE 102, 699–716 (2014).

    Article  Google Scholar 

  37. Hoffmann, M. et al. Unveiling the double-well energy landscape in a ferroelectric layer. Nature 565, 464–467 (2019).

    Article  CAS  PubMed  Google Scholar 

  38. Boescke, T., Muller, J., Brauhaus, D., Schroder, U. & Bottger, U. Ferroelectricity in hafnium oxide thin films. Appl. Phys. Lett. (2011).

  39. Beyer, S. et al. FeFET: A versatile CMOS compatible device with game-changing potential. In 2020 IEEE International Memory Workshop (IMW) 1–4 (IEEE, 2020).

  40. Dally, W. J. & Towles, B. P. Principles and Practices of Interconnection Networks (Elsevier, 2004).

  41. Bi, G. & Poo, M. Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J. Neurosci. 18, 10464–10472 (1998).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  42. Mead, C. Neuromorphic electronic systems. Proc. IEEE 78, 1629–1636 (1990). This paper introduced neuromorphic computing.

    Article  Google Scholar 

  43. Grollier, J. et al. Neuromorphic spintronics. Nat. Electron. 3, 360–370 (2020).

    Article  Google Scholar 

  44. Leugering, J., Nieters, P. & Pipa, G. A minimal model of neural computation with dendritic plateau potentials. Preprint at bioRxiv (2022).

  45. Beniaguev, D., Segev, I. & London, M. Single cortical neurons as deep artificial neural networks. Neuron 109, 2727–2739.e3 (2021).

    Article  CAS  PubMed  Google Scholar 

  46. Wetzstein, G. et al. Inference in artificial intelligence with deep optics and photonics. Nature 588, 39–47 (2021).

    Article  Google Scholar 

  47. Szatmary, B. & Izhikevich, E. Spike-timing theory of working memory. PLoS Comput. Biol. (2010).

  48. Frady, E. & Sommer, F. Robust computation with rhythmic spike patterns. Proc. Natl Acad. Sci. USA 116, 18050–18059 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  49. Goltz, J. et al. Fast and energy-efficient neuromorphic deep learning with first-spike times. Nat. Mach. Intell. 3, 823–835 (2021).

    Article  Google Scholar 

  50. Madhavan, A., Sherwood, T. & Strukov, D. Race logic: abusing hardware race conditions to perform useful computation. IEEE Micro 35, 48–57 (2015).

    Article  Google Scholar 

  51. Tzimpragos, G. et al. Temporal computing with superconductors. IEEE Micro 41, 71–79 (2021).

    Article  Google Scholar 

  52. Borgeaud, S. et al. Improving language models by retrieving from trillions of tokens. In Proceedings of the 39th International Conference on Machine Learning (eds Chaudhuri, K. et al.) 2206–2240 (ICML, 2022).

  53. Braun, W. & Memmesheimer, R. M. High-frequency oscillations and sequence generation in two-population models of hippocampal region CA1. PLoS Comput. Biol. 18, e1009891 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  54. Pulikkottil, V. V., Somashekar, B. P. & Bhalla, U. S. Computation, wiring, and plasticity in synaptic clusters. Curr. Opin. Neurobiol. 70, 101–112 (2021).

    Article  CAS  PubMed  Google Scholar 

  55. Mahowald, M. An Analog VLSI System for Stereoscopic Vision Vol. 265 (Springer Science & Business Media, 1994).

  56. Mead, C. How we created neuromorphic engineering. Nat. Electron. 3, 434–435 (2020).

    Article  Google Scholar 

  57. Henighan, T. et al. Scaling laws for autoregressive generative modeling. Preprint at (2020).

  58. Hoffmann, J. et al. Training compute-optimal large language models. Preprint at (2022).

  59. Diorio, C., Hasler, P., Minch, A. & Mead, C. A. A single-transistor silicon synapse. IEEE Trans. Electron Devices 43, 1972–1980 (1996). An early realization of vector-matrix multiplication inside a 2D memory chip with floating-gate transistors, precursors to the charge-trap transistors that today’s 3D memory chips use.

    Article  CAS  Google Scholar 

  60. Boerlin, M., Machens, C. K. & Denève, S. Predictive coding of dynamical variables in balanced spiking networks. PLoS Comput. Biol. 9, e1003258 (2013).

    Article  PubMed  PubMed Central  Google Scholar 

  61. Kulik, A. et al. Compartment-dependent colocalization of Kir3.2-containing K+ channels and GABAB receptors in hippocampal pyramidal cells. J. Neurosci. 26, 4289–4297 (2006).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  62. Kohl, M. M. & Paulsen, O. The roles of GABAB receptors in cortical network activity. Adv. Pharmacol. 58, 205–229 (2010).

    Article  CAS  PubMed  Google Scholar 

  63. Mainen, Z. & Sejnowski, T. Influence of dendritic structure on firing pattern in model neocortical neurons. Nature 382, 363–366 (1996).

Download references


This work was supported by US Office of Naval Research (grant numbers N000141310419 and N000141512827), US National Science Foundation (grant number 2223827), Stanford Medical Center Development (Discovery Innovation Fund), Stanford Institute for Human-Centered Artificial Intelligence (HAI), C. Reynolds and GrAI Matter Labs. I thank P. Sterling for his help editing the manuscript.

Author information

Authors and Affiliations



K.B. conceived, performed and wrote up this work.

Corresponding author

Correspondence to Kwabena Boahen.

Ethics declarations

Competing interests

K.B. is a co-founder and stockholder of Femtosense Inc. and an advisor to Radical Semiconductor.

Peer review

Peer review information

Nature thanks Dilip Vasudevan and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

This file contains 3 sections: Energy per inference for GPT-3 on Pixel-4; Wiring analysis; and Dendrite model.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Boahen, K. Dendrocentric learning for synthetic intelligence. Nature 612, 43–50 (2022).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing